A Drug-Target Interaction Identification Method Based on the Principle of Implications and Network Topological Structure Features

Abstract

The invention discloses a drug-target interaction identification method based on the principle of implicated crime and network topology features. Firstly, based on human protein-protein interaction data and drug-target interaction data, a drug-target interactome network including protein-protein interaction subnetwork, drug-target interaction subnetwork and drug-drug relationship subnetwork is constructed; Use information such as protein primary structure descriptors, drug molecular fingerprint features, and interaction reliability to weight nodes and edges in the network; based on the principle of implicated crimes and graph theory, a new network topology feature is proposed to characterize drug-target interactions Right; Finally, a random forest algorithm was used to build a model to predict potential drug-target interactions at the proteome scale. This method does not require information such as the three-dimensional structure of proteins and drug molecules, and is simpler, faster and more accurate, and is expected to be applied in the fields of new drug development and pathology research.

Description

technical field [0001] The invention belongs to the technical field of computer aided drug design. More specifically, it relates to a drug-target interaction identification method based on the principle of implicative crime and network topology features. Background technique [0002] The research and development of new drugs has always been a time-consuming and laborious process. It is estimated that it takes an average of billions of dollars and more than a decade to bring a new drug to market. In recent years, the success rate of new drug development has been declining, and one of the main reasons for this phenomenon is the lack of drug-target interaction information. Most drugs are biologically active small molecules, which mainly block abnormal biological processes through the interaction with target proteins. Therefore, identifying drug-target interactions has always been an important part of drug development. Identifying drug-target interactions can not only reduce ...

AI Technical Summary

Problems solved by technology

Using protein primary structure descriptors and drug molecular fingerprint descriptors to characterize drug-target interaction pairs is a simple method, through which drug-target interaction pairs can be represented as a high-dimensional feature vector, but this method does not Consider the integrity and robustness of biological networks

Therefore, in recent years, researchers have proposed a network-based drug-target interaction identification method, but this method only simulates the drug-target interaction as a bipartite graph, and does not take into account the interactions between proteins and proteins and between drugs. , and only consider the protein and drug as a simple point, ignoring the physical and chemical properties

Images